Showing papers on "False positive paradox published in 1976"
TL;DR: It is shown that min L is a generalization of the one-sided two-sample Kolmogorov-Smirnov statistic, and, indeed, exactly equivalent to that statistic for appropriate choices of v and mu.
Abstract: Suppose a continuous diagnostic measurement is used to classify patients, and suppose E1 false negative errors and E2 false positive errors result. The quantities E1 and E2, and the total number of misclassifications, L = E1 + E2, depend on the choice of cut-off value. We have determined the null distribution of min L, where minimization is over all possible cut-off values. The statistic, min L, can be used as a quick one-sided two-sample test, and min L is also useful for evaluating publications which present only a 2 X 2 table of false positives, false negatives, true positives and true negatives. In such cases, one can use min L to assess the usefulness of the diagnostic measurement, even if one suspects that the authors chose that particular cut-off value which minimized L after looking at the data. We extend these results to a more general weighted loss L = vE1 + MUE2 where v and mu are positive integers, and we show that min L is a generalization of the one-sided two-sample Kolmogorov-Smirnov statistic, and, indeed, exactly equivalent to that statistic for appropriate choices of v and mu.
64 citations
TL;DR: Applying basic decision theory on a neuropsychiatric hospital population indicates that researchers using a prediction schedule will be unlikely to predict a future suicide beyond a 20% level of efficiency.
Abstract: Efforts to predict a future event assume varying levels of confidence depending on its base rate and the error rate of the prediction instrument. Most researchers working with suicide prediction instruments seem tacitly to assume they will be able to predict a future suicide most of the time. Applying basic decision theory on a neuropsychiatric hospital population indicates that researchers using a prediction schedule will be unlikely to predict a future suicide beyond a 20% level of efficiency. Contrary to the general clinical view, eliminating false negatives was shown to be more practical than eliminating false positives in increasing the efficiency of a predictive schedule.
33 citations
TL;DR: A previously described vision screening procedure was administered to 652 elementary school children, using lay volunteers and optometrists, using the Modified Clinical Technique (MCT) as the standard.
Abstract: A previously described vision screening procedure was administered to 652 elementary school children, using lay volunteers. These students were later screened by optometrists, using the Modified Clinical Technique (MCT). Using MCT as the standard, the lay screening correctly identified 90% of the children; the incorrect identifications included 28 children (4.3%) as false negatives and 36 children (5.5%) as false positives. Analysis indicates a lower cost for the combined lay and professional screening than for professional screening alone.
15 citations
TL;DR: The use of an agglutination test as a routine diagnostic aid for tuberculosis is found to be both useful and reliable in clinical practice, and the major advantage of the test is its speed, serological diagnosis being available overnight as compared with an average of one month for diagnosis by culture.
Abstract: This study reports the use of an agglutination test as a routine diagnostic aid for tuberculosis. We have found this to be both useful and reliable in clinical practice. The overall reliability was greater than 90%, 13 false results being obtained in the 222 patients tested. False negatives (4) were less common than false positives (9). The major advantage of the test is its speed, serological diagnosis being available overnight as compared with an average of one month for diagnosis by culture.
13 citations
TL;DR: It is suggested that when a positive result in a passive haemagglutination test can be removed by absorption or if positive after absorption cannot be confirmed by other tests for hepatitis Bs antigen, the patient from whom the serum specimen was taken should be investigated for indications of current EB virus infection.
Abstract: Sera from 627 students entering Colleges of Education between 1969 and 1972 were tested for hepatitis B surface antigen and antibody. One was found positive for antigen, none for antibody. Six for 15 positive Hepanosticon results and two positive Hepatest results occurred in sera which also gave positive heterophil antibody tests indicative of current or recent EB virus infection. One of these six sera was still positive in the Hepanosticon test after one absorption, and one of two Hepatests gave no positive reaction with the control cells. Eleven of 14 sera from cases of infectious mononucleosis gave positive Hepanosticon results and two were still positive after one absorption. Seven were positive in the Hepatest and only three of these were positive with the control cells. The control tests in the Hepanosticon and Hepatest do not clearly identify all false positives due to Paul Bunnell antibody. It is suggested that when a positive result in a passive haemagglutination test can be removed by absorption or if positive after absorption cannot be confirmed by other tests for hepatitis Bs antigen, the patient from whom the serum specimen was taken should be investigated for indications of current EB virus infection.
3 citations